AI model · Qwen
Qwen3 VL 8B Thinking
Model ID: qwen/qwen3-vl-8b-thinking
- Input
- $0.18 per 1M tokens
- Output
- $2.10 per 1M tokens
- Context
- 131K tokens at once
- Max output
- 33K tokens per reply
- Released
- 14 Oct 2025 Qwen
What it can do
- YesReasoning
- YesTool calling
- YesImage input
- YesOpen weights
- NoFree to use
Takes image, text; gives text.
How its listing describes it
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
Sources
- Qwen: Qwen3 VL 8B Thinking on OpenRouter — read 2 Oct 2026